.png){kind=icon}
.png){kind=icon}
Return
Knowledge Graph Fusion Based Semantic Communication Framework
.png){kind=icon}
PRE
AI
DOI：10.1109/TMC.2025.3583605.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Semantic communication (SemCom), a paradigm that emphasizes conveying the meaning of information, faces challenges in precise reasoning in semantic coding models. Knowledge graphs (KGs) offer a potential solution by providing structured triples (entities and relations), enabling inference via entity attributes and relational logic. Several key challenges exist in leveraging KGs within SemCom. The first challenge lies in developing methods to create semantic representations aligning and integrating source data and KG information. Second, reconstructing the original data using KGs becomes challenging particularly under poor communication conditions. Moreover, integrating KGs with source data inevitably increases the transmission overhead. In this paper, we propose a novel SemCom framework named KG-SemCom with sophisticated KG-based semantic encoding and decoding designs to solve these challenges. This framework aligns KG entities with message tokens, and then encodes messages into a semantic fusion of contextual and knowledge-based information. Furthermore, KG-SemCom can utilize the KG and contextual relationships to assist in predicting incomplete or distorted messages during the decoding process. Finally, simulation results demonstrate that KG-SemCom achieves higher accuracy and greater robustness compared to existing benchmarks without incorporating KGs, especially in challenging communication environments.
Keywords:
Semantics
Cognition
Decoding
Accuracy
Knowledge graphs
Channel coding
Transformers
Transceivers
Syntactics
Receivers
Semantic communication
knowledge graph
knowledge embedding
semantic communication theory
Journal
IF:
9.2
Papers:
5.6K
Citations:
1.8W